|Publication number||US7054943 B1|
|Application number||US 09/559,065|
|Publication date||May 30, 2006|
|Filing date||Apr 28, 2000|
|Priority date||Apr 28, 2000|
|Also published as||US7356602, US7756989, US20060129687, US20080215742|
|Publication number||09559065, 559065, US 7054943 B1, US 7054943B1, US-B1-7054943, US7054943 B1, US7054943B1|
|Inventors||German Goldszmidt, Jean A. Lorrain, Kiyoshi Maruyama, Dinesh Chandra Verma|
|Original Assignee||International Business Machines Corporation|
|Export Citation||BiBTeX, EndNote, RefMan|
|Patent Citations (14), Referenced by (77), Classifications (14), Legal Events (5)|
|External Links: USPTO, USPTO Assignment, Espacenet|
1. Field of the Invention
The present invention relates generally to a world-wide network, and more particularly to sites of a plurality of Internet World Wide Web (WWW) sites of various owners hosted by a service provider using a group of servers and meeting with agreed-upon service levels.
2. Description of the Related Art
The Internet is the world's largest network, and it has become essential to businesses as well as to consumers. Many businesses have started out-sourcing their e-business and e-commerce Web sites to service providers, instead of operating their Web sites on their own server(s) and managing them by themselves. Such a service provider must install a collection of servers in a farm called a “Web Server Farm (WSF)”, or a “Universal Server Farm (USF)” which can be used by many different businesses to run their e-commerce and e-business applications. These business customers (e.g., the service provider's “customers”) have different “server resource” requirements for their Web sites and applications.
When businesses (hereafter referred to as “customers” or “customers of a server farm”) out-source their e-commerce and/or e-business to a service provider, they must obtain some guarantee on the services they are getting (and will continue to obtain) from the service provider for their sites. Once the service provider has made a commitment to a customer to provide a certain “level” of service (e.g., referred to as a “Service Level Agreement (SLA)”), the provider must guarantee that level of service to that customer.
However, a problem with the conventional system and method used thereby is that, hitherto the present invention, there has been no provision for dynamically equipping the server farm such that server(s) and their resources can be dynamically allocated. Hence, there has been no flexibility in dynamically allocating servers and their resources to customers as the customer's demands change. This results in system-wide inefficiency and general dissatisfaction by the customer.
Another problem with the conventional system is that there are no Service Level Agreements (SLAs) based on dynamic allocation and de-allocation of servers to customer's server clusters.
Yet another problem with the conventional system is that there is no provisioning of SLAs in support of both a guaranteed number of servers and optional additional servers based on the workload changes to customers' applications. Yet another problem with the conventional system is that a “hacker” or “hackers” can generate a large amount of workload to a customer's sites or to the server farm itself to “crash” servers or server farm.
In view of the foregoing and other problems of the conventional methods and structures, an object of the present invention is to provide a method and structure in which an allocation of server resources for a plurality of customers is dynamically controlled.
Another object of the present invention is to support the (minimum, maximum) server resource-based service level agreements for a plurality of customers.
Yet another object of the present invention is to control the allocation of additional server resources to a plurality of customers using the bounds on given service level metrics.
Still another object of the present invention is to support various service level metrics.
A further object of the present invention is to support the use of different metrics for different customers.
Another object of the present invention is to use a service level metric, the amount of allocated resources, and the inbound traffic rate, for defining the state of the current service level (M,N,R) for each customer.
Another object of the present invention is to use a “target” service level metric Mt to keep the actual service level M close to the target service level.
A further object of the present invention is to compute a “target” amount of resources Nt and the inbound traffic rate Rt from a given Mt and (M,N,R).
Still another object of the present invention is to provide and use formulas for computing Nt and Rt from Mt and (M,N,R).
A still further object of the present invention is to allow the use of numerical analysis or quick simulation techniques for deriving Nt and Rt in place of using formulas invented and described in this patent application.
Yet another object of the present invention is to support resource utilization U for M, average response time T for an actual service level M, and the response time percentile T% for the actual service level M (and therefore, the support of targets Ut, Tt and Tt%).
Another object of the present invention is to provide a method (decision algorithm) for deciding whether or not to add additional server resource(s) or to reduce (“throttle down”) the inbound traffic to meet the service level agreements for a plurality of customers.
In a first aspect of the present invention, a method (and system) for managing and controlling allocation and de-allocation of resources based on a guaranteed amount of resource and additional resources based on a best effort for a plurality of customers, includes dynamically allocating server resources for a plurality of customers, such that the resources received by a customer are dynamically controlled and the customer receives a minimum (e.g., a minimum that is guaranteed) amount of resources as specified under a service level agreement (SLA).
In another aspect, a program storage device is provided for storing the program of the inventive method.
With the unique and unobvious features of the present invention, a server farm is equipped with a means to dynamically allocate servers (or server resources) to customers as demands change.
It is noted that a general service level agreement (SLA) on a server resource for a customer can be denoted by (Smin#(i), Smax#(i), Mbounds(i)), where Smin#(i) denotes the guaranteed minimum amount of server resources (e.g., the number of servers), Smax(i) denotes the upper bound on the amount of server resources that a customer may want to obtain when free resources are available, and Mbounds(i) gives two bounds: Mhighbound(i) and Mlowbound(i) on a service level metric M that is used in controlling the allocation of resources beyond the minimum for each i-th customer. Mhighbound(i) is used to decide when to add additional server resources and Mlowbound (i) is used to decide when to remove some server resources.
The minimum (or min) amount of server resources (e.g., number of servers) Smin#(i) is a guaranteed amount of server resources that the i-th customer will receive regardless of the server resource usage. The maximum (or max) amount of server resources Smax#(i) is the upper bound on the amount of server resources that the i-th customer may receive beyond the minimum provided that some unused server resources are available for allocation.
Therefore, the range between Smin#(i) and Smax#(i) represents server resources that are provided on an “as-available” or “best-effort” basis, and it is not necessarily guaranteed that the customer will obtain these resources at any one time, if at all. The allocation of additional resource(s) is performed so as to keep the performance metric within Mbounds(i).
Examples of Mbounds(i) include: (1) the bound on the server resource utilization that is denoted by Ubounds(i); (2) the bound on the average server response time that is denoted by Tbounds(i); and (3) the bound on the server response time percentile that is denoted by T%bounds(i).
Table 1 provides definitions and notations used throughout the present application. For example, when Mbounds(i)=Ubounds(i)=(Ulowbound(i),Uhighbound(i)=(50%, 80%), the server farm tries to allocate additional server resources (or de-allocate some servers) to the i-th customer's server complex to keep the server resource utilization between 50% and 80%.
That is, when the server resource utilization goes above 80%, the server farm tries to keep the utilization below 80% by allocating additional server resources to the i-th customer when free resources are available. If free resources are not available, the server farm may need to limit the amount of incoming traffic to the i-th customer's server complex. Conversely, when the server resource utilization goes below 50%, the server farm tries to remove some server resources from the i-th customer in order to keep the utilization above 50%. In order to keep the observed metric M within the given Mbounds, the notion of a “target” metric Mt is introduced. Mt is a value that falls between Mlowbound and Mhighbound and the system of the present invention tries to keep the observed metric M as close as possible to the target metric Mt by adjusting server resources. In general, the unit cost of the server resources above the minimum guarantee is more than or equal to that of the server resources below the minimum.
Thus, the present invention provides a dynamic resource allocation to a plurality of customers to meet with the (min, max) server resources and performance metric based service level agreements. Unused (un-allocated) server resources are pooled and allocated and de-allocated from the pool, thus providing sharing of server resources among plurality of customer, leading to efficient use of server resources. Since incoming workload is regulated when it has exceeded server resources allocated, the system provides a “denial of services” to some workloads, thus preventing a crash of hosted customer sites and preventing a crash of the server farm itself.
The foregoing and other purposes, aspects and advantages will be better understood from the following detailed description of a preferred embodiment of the invention with reference to the drawings, in which:
Referring now to the drawings, and more particularly to
As shown in
Then, the inventive system performs the following actions only when M(i) falls outside of Mbounds(i), namely either M(i) is above Mhighbound(i) or M(i) is below Mlowbound(i), to avoid “allocation/de-allocation swings”.
The “target” amount of server resources Nt(i), without changing the inbound traffic R(i), is computed. Further, the “target” inbound traffic rate Rt(i), without changing the allocated resource N(i), is computed in order to bring the service level metric M(i) close to the “targeted” service level metric Mt(i) from monitored R(i), N(i) and M(i) for all i. The target service level metric Mt(i) is the service level metric at or near which one wants to keep M(i) so that M(i) falls within Mbounds(i)=(Mlowbound(i),Mhighbound(i)).
Once Nt(i) and Rt(i) are computed, then it is decided how to move current M(i) to the target Mt(i), by either changing N(i) to Nt(i) (e.g., this involves either allocating server resources from free resource pool 203 to a customer's server set 201 or 202, or taking some server resources away from customer 201 or 202 and return to the pool 203) or by bounding the inbound traffic rate R(i) to Rt(i) (e.g., this is performed when either the maximum amount of resources has been already allocated or no free resource is available so that the only way to bring M(i) to Mt(i) is to reduce the amount of inbound traffic).
Once the decision has been made, it will then send a request to an appropriate systems resource manager (e.g., a “resource allocation manager” or an “inbound traffic controller”).
It is noted that the operation space D 304 could be made available especially when a server farm operator could “borrow” some servers from some customers when the customers are not fully utilizing their resources.
The operation space B 302 is a “non-desirable” space since the service level metric M is exceeding the bound Mhighbound 311. The operation space E 305 is the space in which the operational state should be kept. Furthermore, the upper portion of the space E 305 that is bounded by Mlowbound 312 and Mhighbound 311 is the operation space allowed by the exemplary service level agreement (SLA) that the present invention supports. It is noted that the metric M may be utilization, average response time, percentile response time, etc. Mbounds 307 may be Ubounds, Tbounds, T%bounds, etc. as suitably determined by the designer given constraints and requirements imposed thereon.
In the present invention, the operation state which falls into the green belt 405 is deemed to be acceptable while the operation which falls outside of the green belt (e.g., below the green belt), is not acceptable since too many unnecessary resources are allocated, thereby incurring extra (wasteful) costs to a customer.
An object of the dynamic resource allocation according to the present invention is to keep the operation state within the green belt 405. When the current operation state that is denoted by (M,N,R) is at 403 in the space 305, the primary operation is to reduce the currently allocated amount of resources N to the target amount Nt, so that the service level metric M at 403 would move to the target metric Mt at 404.
When the current operation state that is denoted by (M,N,R) is at 402 in the space 302, the current resource N may be increased to Nt when some free resources are available for allocation, or the inbound traffic R may be reduced to Rt so that metric M at 402 would move to Mt at 404. When the current state is within the green belt 405, no action is taken. The green belt 405 therefore defines the allowable system operation state region such that any state within the green belt 405 meets the service level agreement (SLA).
The main system 501 includes a decision module and methodology 503 (e.g., algorithm), a module 502 (algorithm) for computing targets Nt(i) and Rt(i), and a repository for storing Service Level Agreements (SLA) 504.
The module 502 computes the target values Nt(i) and Rt(i) from the monitored data M(i) 204, N(i) 205 and R(i) 206 for every customer whenever its operation state (M(i),N(i),R(i)) falls outside of the green belt 405 associated with the customer.
Then the decision module 503, using the SLA information, (M(i),N(i),R(i)), Nt(i) and Rt(i), decides what action to take.
That is, the decision module 503 decides either to change the current resource amount from N(i) to Nt(i) 508, or bound the current inbound traffic rate R(i) by Rt(i) 505, and then take appropriate action.
System 501 has a communications means to instruct “server resource manager” 509 to change resource allocation 510. The system 501 has a communications means to instruct “inbound traffic controller” 506 to bound the incoming traffic 507 to a specific customer site (201 or 202).
Tables 2 through 5 give various means in computing or deriving target values Nt(i) and Rt(i) for every customer i.
For example, Table 2 describes formulas for computing these targets when the service level metric M is the resource utilization U.
Table 3 describes a formula for computing these targets when the service level metric M is the average response time T. Here, the average response time was derived from the “M/M/m” multi-server queuing model.
It is noted that since the computation is used for the “hill climbing” optimization and is repeated periodically, and the amount of resources allocated or de-allocated at each step is assumed to be very small compared to the amount of resources currently allocated, the use of “M/M/m” model should be quite acceptable even though the arrival rate might be different from Poisson and the job processing time may not be exponentially distributed. A major advantage of “M/M/m” model is that it offers the closed form formula as shown in Table 3.
Table 4 describes formulas for computing these targets when the service level metric M is the response time percentile T%. Again, the “M/M/m” queuing model is assumed in computing the targets.
Table 5 shows that, instead of using a formula to compute the targets (Nt,Rt), one could use any numerical computation tool or quick simulation tool.
The decision method 600 looks for (e.g., attempts to obtain) potential revenue maximization opportunity when allocating free resources to various customers. It first seeks any opportunity to de-allocate resources, next allocates additional resources to customers whose service level metric is outside of the green belt 405 (
Method 600 begins at step 601. In step 602, the target values (Nt(i),Rt(i)) are computed for every i. Further, the variable “ITC-informed(i)”=“no” is set for all “i”. This variable keeps a record of whether or not throttling on inbound traffic has been applied or not prior to the current computation. This computation or examination is performed periodically to check whether or not any service level agreements have been violated, that is, checking whether or not any operation states falls outside of green belts. An examination is conducted in a time interval called a cycle-time. A cycle-time is a system operation configuration parameter. For example, a cycle time value could be selected from a value between 1 second to 60 seconds. Whether to choose a smaller value or a larger value depends on how fast one can adjust resource allocation/de-allocation.
In step 603, it is determined whether or not the service cycle time has expired. If it has expired (e.g., a “YES” in step 603), the process loops back to step 602.
If “NO” in step 603, then in step 604 it is checked whether the operation state M(i) is within the green belt 405 (e.g., see FIG. 4).
If so (e.g., a “YES”), then step 605 is executed in which the system waits for the cycle time to elapse and the process loops back to step 602.
If “NO” in step 604, then in step 606, it is checked whether any customer exists such that the target resource amount Nt(i) is less than the current amount N(i) (i.e., seeking an opportunity to de-allocate server resources from customers and placing them back into the pool of “free” resources).
If “YES” in step 606, one possibility that Nt(i) is less than N(i) is that because the inbound traffic has been throttled. This condition is tested at step 607. Step 606 identifies all those customers such that Nt(i) is less than N(i). Step 607 is applied to only those customers identified in step 606. Step 607 checks if there is any customer whose inbound traffic is currently throttled. If step 607 is “YES”, step 609 is executed. Step 609 issues a command to ITC 506 to stop applying the throttling on the i-th customer's inboud traffic. and sets ITC-informed (i)=“no”.
When Nt(i) is less than N(i) (“YES” in step 606) and the inbound traffic is not throttled (“NO” in step 607), that means that too many resources have been allocated to the given amount of inbound traffic for the i-th customer traffic, step 608 seeks to de-allocate resources away from the i-th customer.
In step 610, it is checked whether the resource(s) must be increased for any customer identified in step 606. There is no action required for those customers whose target value Nt(i) is equal to the observed value N(i). Step 610 identifies a customer whose server resource must be increased.
If so (“YES” in step 610) and if free resources are available (“YES” in step 611), then step 612 is executed to allocate additional resources (e.g., allocate up to Nt(i)−N(i) resources without exceeding Smax#(i)).
When additional resources must be allocated, and yet no free resource is available (e.g., a “NO” in step 611), then it is necessary to “re-claim” resources from those customers who have more than the guaranteed minimum (e.g., N(j)>Smin#(j)) (step 614).
When additional resource(s) must be allocated (“YES” in step 610), and no free resource is available (“NO” in step 611) and if the currently allocated resource N(i) is more than or equal to the guaranteed minimum Smin#(i) (“NO” in step 613), then the inbound traffic must be throttled (step 615). That is, the inbound traffic controller 506 is instructed to bound the traffic by Rt(i), and ITC-informed(i) is set to “YES”.
As described above, with the unique and unobvious features of the present invention, a dynamic resource allocation is provided to a plurality of customers to meet with the (min,max) server resources and performance metric-based service level agreements.
When describing the embodiment of this invention, often a fixed size unit of allocable or de-allocable resources were assumed. However, one can easily generalize to the case where each allocable unit has a different amount.
Further, it is noted that the method of the invention may be stored on a storage medium as a series of program steps, and can be executed by a digital data processing apparatus.
While the invention has been described in terms of a preferred embodiment, the invention is not limited thereto and those skilled in the art will recognize that the invention can be practiced with modification within the spirit and scope of the appended claims.
|Cited Patent||Filing date||Publication date||Applicant||Title|
|US5461611 *||Jun 7, 1994||Oct 24, 1995||International Business Machines Corporation||Quality of service management for source routing multimedia packet networks|
|US5719854 *||Apr 5, 1996||Feb 17, 1998||Lucent Technologies Inc.||Efficiently providing multiple grades of service with protection against overloads in shared resources|
|US5799173 *||May 21, 1997||Aug 25, 1998||International Business Machines Corporation||Dynamic workload balancing|
|US5838686||Apr 22, 1994||Nov 17, 1998||Thomson Consumer Electronics, Inc.||System for dynamically allocating a scarce resource|
|US5892754 *||Jun 7, 1996||Apr 6, 1999||International Business Machines Corporation||User controlled adaptive flow control for packet networks|
|US5915095 *||Aug 8, 1995||Jun 22, 1999||Ncr Corporation||Method and apparatus for balancing processing requests among a plurality of servers based on measurable characteristics off network node and common application|
|US6154778 *||May 19, 1998||Nov 28, 2000||Hewlett-Packard Company||Utility-based multi-category quality-of-service negotiation in distributed systems|
|US6167445 *||Oct 26, 1998||Dec 26, 2000||Cisco Technology, Inc.||Method and apparatus for defining and implementing high-level quality of service policies in computer networks|
|US6335927 *||Nov 18, 1996||Jan 1, 2002||Mci Communications Corporation||System and method for providing requested quality of service in a hybrid network|
|US6459682 *||Apr 7, 1998||Oct 1, 2002||International Business Machines Corporation||Architecture for supporting service level agreements in an IP network|
|US6463454 *||Jun 17, 1999||Oct 8, 2002||International Business Machines Corporation||System and method for integrated load distribution and resource management on internet environment|
|US6502131 *||Dec 4, 1998||Dec 31, 2002||Novell, Inc.||Directory enabled policy management tool for intelligent traffic management|
|US6580721 *||Aug 11, 1998||Jun 17, 2003||Nortel Networks Limited||Routing and rate control in a universal transfer mode network|
|US20020174227 *||Jun 12, 2001||Nov 21, 2002||Hartsell Neal D.||Systems and methods for prioritization in information management environments|
|Citing Patent||Filing date||Publication date||Applicant||Title|
|US7155380||Dec 9, 2004||Dec 26, 2006||Microsoft Corporation||System and method for designing a logical model of a distributed computer system and deploying physical resources according to the logical model|
|US7243374||Aug 8, 2001||Jul 10, 2007||Microsoft Corporation||Rapid application security threat analysis|
|US7310672 *||Nov 13, 2001||Dec 18, 2007||Hewlett-Packard Development Company, L.P.||Method and system for exploiting service level objectives to enable resource sharing in a communication network having a plurality of application environments|
|US7370103 *||Nov 12, 2004||May 6, 2008||Hunt Galen C||System and method for distributed management of shared computers|
|US7395320||Jun 1, 2005||Jul 1, 2008||Microsoft Corporation||Providing automatic policy enforcement in a multi-computer service application|
|US7406517||Nov 1, 2004||Jul 29, 2008||Microsoft Corporation||System and method for distributed management of shared computers|
|US7428593 *||Feb 11, 2005||Sep 23, 2008||Broadcom Corporation||System and method of processing data flow in multi-channel, multi-service environment by dynamically allocating a socket|
|US7464163 *||Jul 27, 2000||Dec 9, 2008||International Business Machines Corporation||Service provisioning via attribute-based subscription|
|US7536461 *||Jul 21, 2005||May 19, 2009||International Business Machines Corporation||Server resource allocation based on averaged server utilization and server power management|
|US7543060 *||Jul 3, 2001||Jun 2, 2009||Fujitsu Limited||Service managing apparatus for keeping service quality by automatically allocating servers of light load to heavy task|
|US7669235||May 25, 2004||Feb 23, 2010||Microsoft Corporation||Secure domain join for computing devices|
|US7684964||Sep 8, 2005||Mar 23, 2010||Microsoft Corporation||Model and system state synchronization|
|US7689676||Jan 12, 2007||Mar 30, 2010||Microsoft Corporation||Model-based policy application|
|US7711121||Nov 2, 2004||May 4, 2010||Microsoft Corporation||System and method for distributed management of shared computers|
|US7739380||Nov 12, 2004||Jun 15, 2010||Microsoft Corporation||System and method for distributed management of shared computers|
|US7778422||Feb 27, 2004||Aug 17, 2010||Microsoft Corporation||Security associations for devices|
|US7792931||Mar 10, 2005||Sep 7, 2010||Microsoft Corporation||Model-based system provisioning|
|US7797147||Apr 15, 2005||Sep 14, 2010||Microsoft Corporation||Model-based system monitoring|
|US7802144||Apr 15, 2005||Sep 21, 2010||Microsoft Corporation||Model-based system monitoring|
|US7809832||Jun 25, 2008||Oct 5, 2010||Broadcom Corporation||System and method of processing data flow in multichannel, multi-service environment by dynamically allocating a socket|
|US7886041||Mar 1, 2004||Feb 8, 2011||Microsoft Corporation||Design time validation of systems|
|US7890543||Oct 24, 2003||Feb 15, 2011||Microsoft Corporation||Architecture for distributed computing system and automated design, deployment, and management of distributed applications|
|US7890951||Jun 29, 2005||Feb 15, 2011||Microsoft Corporation||Model-based provisioning of test environments|
|US7912956 *||Jan 22, 2008||Mar 22, 2011||Raytheon Company||Service level agreement based control of a distributed computing system|
|US7917625 *||Jan 14, 2005||Mar 29, 2011||Sprint Communications Company L.P.||Predictive processing resource level control|
|US7941309||Nov 2, 2005||May 10, 2011||Microsoft Corporation||Modeling IT operations/policies|
|US8005956 *||Jan 22, 2008||Aug 23, 2011||Raytheon Company||System for allocating resources in a distributed computing system|
|US8117505 *||Nov 7, 2005||Feb 14, 2012||Microsoft Corporation||Resource exhaustion prediction, detection, diagnosis and correction|
|US8122106||Oct 24, 2003||Feb 21, 2012||Microsoft Corporation||Integrating design, deployment, and management phases for systems|
|US8140666 *||Mar 29, 2007||Mar 20, 2012||International Business Machines Corporation||Method and apparatus for network distribution and provisioning of applications across multiple domains|
|US8219358||May 9, 2008||Jul 10, 2012||Credit Suisse Securities (Usa) Llc||Platform matching systems and methods|
|US8327372 *||Feb 19, 2009||Dec 4, 2012||Sprint Communications Company L.P.||Virtualization and server imaging system for allocation of computer hardware and software|
|US8489728||Apr 15, 2005||Jul 16, 2013||Microsoft Corporation||Model-based system monitoring|
|US8516493 *||Feb 1, 2011||Aug 20, 2013||Futurewei Technologies, Inc.||System and method for massively multi-core computing systems|
|US8533103||Sep 14, 2010||Sep 10, 2013||Amazon Technologies, Inc.||Maintaining latency guarantees for shared resources|
|US8549513||Jun 29, 2005||Oct 1, 2013||Microsoft Corporation||Model-based virtual system provisioning|
|US8555335||Nov 1, 2006||Oct 8, 2013||Microsoft Corporation||Securing distributed application information delivery|
|US8612330||Sep 14, 2010||Dec 17, 2013||Amazon Technologies, Inc.||Managing bandwidth for shared resources|
|US8694400||Sep 14, 2010||Apr 8, 2014||Amazon Technologies, Inc.||Managing operational throughput for shared resources|
|US8826287 *||Jan 28, 2005||Sep 2, 2014||Hewlett-Packard Development Company, L.P.||System for adjusting computer resources allocated for executing an application using a control plug-in|
|US8972223||Jun 19, 2012||Mar 3, 2015||Credit Suisse Securities (Usa) Llc||Platform matching systems and methods|
|US8984243||Feb 22, 2013||Mar 17, 2015||Amazon Technologies, Inc.||Managing operational parameters for electronic resources|
|US20020059427 *||Jul 5, 2001||May 16, 2002||Hitachi, Ltd.||Apparatus and method for dynamically allocating computer resources based on service contract with user|
|US20020116479 *||Jul 3, 2001||Aug 22, 2002||Takeshi Ishida||Service managing apparatus|
|US20030033516 *||Aug 8, 2001||Feb 13, 2003||Michael Howard||Rapid application security threat analysis|
|US20030093527 *||Nov 13, 2001||May 15, 2003||Jerome Rolia||Method and system for exploiting service level objectives to enable resource sharing in a communication network having a plurality of application environments|
|US20040210623 *||Mar 6, 2003||Oct 21, 2004||Aamer Hydrie||Virtual network topology generation|
|US20050097058 *||Nov 12, 2004||May 5, 2005||Microsoft Corporation||System and method for distributed management of shared computers|
|US20050097147 *||Nov 1, 2004||May 5, 2005||Microsoft Corporation||System and method for distributed management of shared computers|
|US20050102388 *||Dec 8, 2004||May 12, 2005||Microsoft Corporation||System and method for restricting data transfers and managing software components of distributed computers|
|US20050147124 *||Feb 11, 2005||Jul 7, 2005||Broadcom Corporation||System and method of processing data flow in multi-channel, multi-service environment by dynamically allocating a socket|
|US20050192971 *||Apr 22, 2005||Sep 1, 2005||Microsoft Corporation||System and method for restricting data transfers and managing software components of distributed computers|
|US20050240650 *||Apr 22, 2004||Oct 27, 2005||International Business Machines Corporation||Service enablement via on demand resources|
|US20060069758 *||Jun 1, 2005||Mar 30, 2006||Microsoft Corporation||Providing automatic policy enforcement in a multi-computer service application|
|US20060198507 *||Feb 28, 2006||Sep 7, 2006||Fujitsu Limited||Resource allocation method for network area and allocation program therefor, and network system|
|US20060253464 *||Jan 23, 2004||Nov 9, 2006||Shyamalie Thilakawardana||Method and system for determining optimum resource allocation in a network|
|US20070094379 *||Jul 21, 2005||Apr 26, 2007||International Business Machines Corporation||Server power management|
|US20070106636 *||Nov 7, 2005||May 10, 2007||Microsoft Corporation||Resource exhaustion prediction, detection, diagnosis and correction|
|US20070208463 *||Mar 2, 2006||Sep 6, 2007||International Business Machines Corporation||Learning a predicted voltage to supply an electronic device based on dynamic voltage variation|
|US20080154793 *||Dec 10, 2007||Jun 26, 2008||Netfusion Pty Limited||Method and system for improved outsourcing|
|US20080240150 *||Mar 29, 2007||Oct 2, 2008||Daniel Manuel Dias||Method and apparatus for network distribution and provisioning of applications across multiple domains|
|US20080312988 *||Jun 14, 2007||Dec 18, 2008||Akzo Nobel Coatings International B.V.||Performance rating of a business|
|US20090055234 *||Aug 22, 2007||Feb 26, 2009||International Business Machines Corporation||System and methods for scheduling meetings by matching a meeting profile with virtual resources|
|US20090119673 *||Nov 6, 2008||May 7, 2009||Credit Suisse Securities (Usa) Llc||Predicting and managing resource allocation according to service level agreements|
|US20090161686 *||Jun 25, 2008||Jun 25, 2009||Viresh Rustagi||System and method of processing data flow in multichannel, multi-service environment by dynamically allocating a socket|
|US20090187658 *||Jul 23, 2009||Williams Michael L||System for Allocating Resources in a Distributed Computing System|
|US20090281770 *||May 9, 2008||Nov 12, 2009||Yatko Steven W||Platform matching systems and methods|
|US20100070625 *||Mar 18, 2010||Zeus Technology Limited||Supplying Data Files to Requesting Stations|
|US20110087522 *||Apr 14, 2011||International Business Machines Corporation||Method for deploying a probing environment for provisioned services to recommend optimal balance in service level agreement user experience and environmental metrics|
|US20110238546 *||Sep 29, 2011||Amazon Technologies, Inc.||Managing committed processing rates for shared resources|
|US20110238857 *||Mar 29, 2010||Sep 29, 2011||Amazon Technologies, Inc.||Committed processing rates for shared resources|
|US20120198465 *||Aug 2, 2012||Nitin Hande||System and Method for Massively Multi-Core Computing Systems|
|US20130006686 *||Jun 29, 2011||Jan 3, 2013||International Business Machines Corporation||Managing Organizational Computing Resources in Accordance with Computing Environment Entitlement Contracts|
|US20140156853 *||Jul 12, 2012||Jun 5, 2014||Nec Corporation||Computer and resource retrieval method|
|CN102844772A *||Mar 29, 2011||Dec 26, 2012||亚马逊技术股份有限公司||Managing committed request rates for shared resources|
|EP2553638A1 *||Mar 29, 2011||Feb 6, 2013||Amazon Technologies, Inc.||Managing committed request rates for shared resources|
|WO2011123467A1||Mar 29, 2011||Oct 6, 2011||Amazon Technologies, Inc.||Managing committed request rates for shared resources|
|U.S. Classification||709/229, 709/226, 370/236, 370/231, 718/104|
|Cooperative Classification||H04L67/1029, H04L67/1002, H04L67/306, H04L67/322, H04L67/1031, G06F9/505|
|European Classification||G06F9/50A6L, H04L29/08N31Q|
|Apr 28, 2000||AS||Assignment|
Owner name: IBM CORPORATION, NEW YORK
Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:GOLDSZMIDT, GERMAN;LORRAIN, JEAN A.;MARUYAMA, KIYOSHI;AND OTHERS;REEL/FRAME:010770/0399;SIGNING DATES FROM 20000425 TO 20000426
|Oct 21, 2009||FPAY||Fee payment|
Year of fee payment: 4
|Jan 10, 2014||REMI||Maintenance fee reminder mailed|
|Apr 11, 2014||FPAY||Fee payment|
Year of fee payment: 8
|Apr 11, 2014||SULP||Surcharge for late payment|
Year of fee payment: 7